Assuring Safe and Efficient Operation of UAV Using Explainable Machine Learning

The accurate estimation of airspace capacity in unmanned traffic management (UTM) operations is critical for a safe, efficient, and equitable allocation system resources. While conventional approaches assessing complexity certainly exist, these methods fail to capture true capacity, since they address several important variables (such as weather). Meanwhile, existing AI-based decision-support systems evince opacity inexplicability, this restricts their practical application. With challenges mind, the authors propose tailored solution needs demand (DCM) services. This solution, by deploying synthesized fuzzy rule-based model deep learning will trade-off between explicability performance. In doing so, it generate an intelligent that be explicable reasonably comprehensible. results show advisory able indicate most appropriate regions aerial vehicle (UAVs) operation, also increase UTM availability more than 23%. Moreover, proposed demonstrates maximum gain 65% minimum safety 35%, while possessing explainability attribute 70%. assist authorities through effective formulation new operational regulations performance requirements.